Face Anonymization

Benchmarks archive 2025-07-28

2 leaderboard tables shown for this task, 2 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

3 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

11 shown of 11 papers with code (23 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• DeepPrivacy: A Generative Adversarial Network for Face Anonymization
  10 Sep 2019 2 repositories listed Syntology ran 0 of 10 samples · 10 unverified
  Our model is based on a conditional generative adversarial network, generating images considering the original pose and image background.
• NullFace: Training-Free Localized Face Anonymization
  11 Mar 2025 1 repository listed
  It begins by inverting the input image to recover its initial noise.
• Face Anonymization Made Simple
  1 Nov 2024 1 repository listed
  Current face anonymization techniques often depend on identity loss calculated by face recognition models, which can be inaccurate and unreliable.
• Context-Aware Full Body Anonymization using Text-to-Image Diffusion Models
  11 Oct 2024 1 repository listed
  In order to protect people's privacy whilst keeping important features in the dataset, it is important to replace the full body of a person with a highly detailed anonymized one.
• G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors
  18 Aug 2024 1 repository listed Syntology ran 8 of 11 samples · 3 unverified
  This paper introduces G\textsuperscript{2}Face, which leverages both generative and geometric priors to enhance identity manipulation, achieving high-quality reversible face anonymization without compromising data…
• DisguisOR: Holistic Face Anonymization for the Operating Room
  26 Jul 2023 1 repository listed
  Methods: RGB and depth images from multiple cameras are fused into a 3D point cloud representation of the scene.
• Does Image Anonymization Impact Computer Vision Training?
  8 Jun 2023 1 repository listed
  Furthermore, we find that realistic anonymization can mitigate this decrease in performance, where our experiments reflect a minimal performance drop for face anonymization.
• GANonymization: A GAN-based Face Anonymization Framework for Preserving Emotional Expressions
  3 May 2023 1 repository listed
  The effectiveness of the approach was assessed by evaluating its performance in removing identifiable facial attributes to increase the anonymity of the given individual face.
• LDFA: Latent Diffusion Face Anonymization for Self-driving Applications
  17 Feb 2023 1 repository listed
  Therefore, datasets used to train perception models of ITS must contain a significant number of vulnerable road users.
• DeepPrivacy2: Towards Realistic Full-Body Anonymization
  17 Nov 2022 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  Generative Adversarial Networks (GANs) are widely adapted for anonymization of human figures.
• CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks
  19 May 2020 1 repository listed Syntology ran 0 of 5 samples · 5 unverified
  In many real-world scenarios like people tracking or action recognition, it is important to be able to process the data while taking careful consideration in protecting people's identity.

Syntology lines on 4 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.